Deep learning–based neural networks for day-ahead power load probability density forecasting

Abstract

Highlights•Machine learning promotes energy utilization efficiency for reducing GHG emissions •Hybrid MCQRNN with Dropconnect and Dropout for load probability density forecasting •D-MCQRNN conquers overfitting and alleviates the time-lag of multi-output forecasts •D-MCQRNN improves the accuracy and reliability of load probability density forecasts Manuscript Click here to access/download;Manuscript;Manuscript marked with changes.docx Click here to view linked References